# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# As a condition of accessing this website, you agree to abide by the Content Signals below.
# Content signals are an express reservation of rights under Article 4 of EU Directive 2019/790
# on Copyright in the Digital Single Market, and a website terms-of-use restriction.

# Signal definitions:
#   search   = indexing + linking + short excerpts for traditional search results
#   ai-input = real-time retrieval for AI-generated answers (RAG, grounding, citations)
#   ai-train = use as training/fine-tuning data for AI models

# Our policy:
#   search   = yes  (we want search-engine traffic)
#   ai-input = yes  (we want AI search citations)
#   ai-train = no   (we do not consent to use as training data)

# Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: *
Allow: /

# ============================================================
# AI search bots — ALLOWED
# These bots fetch for real-time citation in AI answers.
# GPTBot doubles as OpenAI's search-discovery crawler;
# Google-Extended is required for inclusion in Google AI Overviews.
# Both are allowed because we want citation in AI answers.
# Training-only crawlers stay blocked (see next section).
# ============================================================

User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Applebot
Allow: /

# ============================================================
# AI training bots — BLOCKED
# These bots ingest content for model training without citation.
# ============================================================

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

Sitemap: https://jaymount.com/sitemap.xml